Agent/knowhub/scripts/salvage_placeholder_strategies.py

#!/usr/bin/env python3
"""
修复 5 个占位 strategy（REQ_004 / 031 / 053 / 066 / 070）：
  把各自的非标准 body schema 正规化成标准 workflow_outline 结构，
  并写 strategy_capability junction（之前 0 条）。

不改 strategy.id / strategy.name / strategy.description（保留原调研的 rich 描述）。
body 里原 schema 字段也保留（作为 salvage_original），只是增加 workflow_outline。

各 folder 的 schema 变体：
  REQ_004: body.strategy.phases + body.capability_mapping (cap by name, phase_id 映射)
  REQ_031: body.strategy.phases[*].capabilities_used (含 'CAP-XXX 名字' 组合字符串)
  REQ_053: body.phases[*].capabilities (dict with id/name) + body.core_workflow
  REQ_066: body.execution_phases[*].capabilities_used (混合 id 和 name)
  REQ_070: body.selected_blueprint.phases[*].capabilities_used

Cap 引用处理：
  1. 若是 'CAP-XXX' 形式且 XXX 存在于 DB → 直接用
  2. 若是 'CAP-tao_dev_1-XX-YY' 老 ID → 通过 MERGE_CLUSTERS 传递闭包解析
  3. 若是纯名字 → 通过 alias map（含 LLM_RENAMES）解析
  4. 解析不到 → 记录到 unresolved，不写 junction
"""
import hashlib
import json
import re
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent.parent.parent))
from knowhub.knowhub_db.pg_capability_store import PostgreSQLCapabilityStore
from knowhub.scripts.merge_capabilities import MERGE_CLUSTERS
from knowhub.scripts.rename_merged_capabilities import RENAMES
from knowhub.scripts.llm_renames import LLM_RENAMES

TARGET_REQS = ['REQ_004', 'REQ_031', 'REQ_053', 'REQ_066', 'REQ_070']

# 占位 strategy 里特有的老 ID / 含混名字 → canonical
# 这些是 MERGE_CLUSTERS 和 LLM_RENAMES 都没覆盖的 salvage-specific refs
LEGACY_REFS = {
    # 老 tao_dev ID
    'CAP-tao_dev_1-02-03': 'CAP-792fd807',   # 景深虚化光学模拟
    'CAP-tao_dev_1-03-01': 'CAP-1649b549',   # 戏剧性明暗对比
    'CAP-tao_dev_1-00-02': 'CAP-008ee6c9',   # 真实感提示词注入
    # REQ_004 的名字变体
    '结构化提示词工程（PROMPT MASTER）': 'CAP-5b000814',
    '参考图融合控制（Omni-Reference）': 'CAP-017',
    '手持道具细节强化': 'CAP-d043d289',
    # REQ_031 的 is_new cap（现已有 canonical）
    '跨物种形态融合生成（is_new）': 'CAP-24dd762b',
    '跨物种形态融合生成': 'CAP-24dd762b',
    # REQ_053 的变体
    '景深虚化光学模拟（前景虚化）': 'CAP-792fd807',
}


def norm(s):
    return (s or '').strip().lower()


def build_alias_and_member(cur):
    """Return (alias_name→canonical, member_id→canonical) with transitive closure."""
    m2c = {}
    for canonical, members in MERGE_CLUSTERS.items():
        for m in members:
            m2c[m] = canonical

    def final(cid, limit=10):
        seen = set()
        while cid in m2c and cid not in seen and limit > 0:
            seen.add(cid); cid = m2c[cid]; limit -= 1
        return cid
    for m in list(m2c.keys()):
        m2c[m] = final(m)

    alias = {}
    cur.execute('SELECT id, name FROM capability')
    db_caps = {r['id']: r['name'] for r in cur.fetchall()}
    for cid, name in db_caps.items():
        alias[norm(name)] = cid
    for cid, (new_name, _) in RENAMES.items():
        alias[norm(new_name)] = final(cid)
    for llm_name, canonical in LLM_RENAMES.items():
        alias[norm(llm_name)] = final(canonical)
    return alias, m2c, db_caps


def resolve_cap(cap_ref, alias, m2c, db_caps, unresolved):
    """cap_ref can be: an id 'CAP-XXX', a name, or 'CAP-XXX 名字' combo."""
    if not cap_ref:
        return None
    cap_ref = str(cap_ref).strip()

    # 0. LEGACY_REFS 优先（占位 strategy 特有的老 ID 和 含混名字）
    if cap_ref in LEGACY_REFS:
        cand = LEGACY_REFS[cap_ref]
        if cand in db_caps:
            return cand

    # Extract leading CAP-... if present
    id_match = re.match(r'^(CAP-[\w\-]+)', cap_ref)
    candidate_id = id_match.group(1) if id_match else None
    # Extract name part
    if id_match:
        name_part = cap_ref[id_match.end():].strip()
    else:
        name_part = cap_ref

    # 1. Direct ID if exists in DB
    if candidate_id and candidate_id in db_caps:
        return candidate_id
    # 2. LEGACY tao_dev_id
    if candidate_id and candidate_id in LEGACY_REFS:
        return LEGACY_REFS[candidate_id]
    # 3. tao_dev old ID through member->canonical transitive closure
    if candidate_id and candidate_id in m2c:
        return m2c[candidate_id]
    # 4. Name alias
    if name_part:
        cand = alias.get(norm(name_part))
        if cand and cand in db_caps:
            return cand
    # 5. Try whole ref as name (for cases where no prefix)
    cand = alias.get(norm(cap_ref))
    if cand and cand in db_caps:
        return cand

    unresolved.append(cap_ref)
    return None


# ═══════════════════════════════════════════════════════════
# Each folder's schema normalizer
def salvage_req_004(body, alias, m2c, db_caps, unresolved):
    """body.strategy.phases + body.capability_mapping (phase_id -> caps)."""
    strat = body.get('strategy', {})
    phases = strat.get('phases', []) if isinstance(strat, dict) else []
    cap_map = body.get('capability_mapping', [])
    # Build phase_id -> [cap_name, ...]
    pid_to_caps = {}
    for cm in cap_map:
        if not isinstance(cm, dict): continue
        cap_name = cm.get('capability')
        for pid in cm.get('used_in_phases', []):
            # pid can be like 'P1', 'P2（备选）' — take prefix P[digit]
            m = re.match(r'(P\d+)', str(pid))
            if m:
                pid_to_caps.setdefault(m.group(1), []).append(cap_name)
    wo = []
    for ph in phases:
        if not isinstance(ph, dict): continue
        pid = ph.get('phase_id', '')
        caps_names = pid_to_caps.get(pid, [])
        resolved = []
        seen = set()
        for n in caps_names:
            r = resolve_cap(n, alias, m2c, db_caps, unresolved)
            if r and r not in seen:
                resolved.append({'id': r, 'name': db_caps.get(r, n)})
                seen.add(r)
        wo.append({
            'phase': ph.get('phase', ''),
            'description': ph.get('description', ''),
            'capabilities': resolved,
        })
    return wo


def salvage_req_031(body, alias, m2c, db_caps, unresolved):
    """body.strategy.phases[*].capabilities_used (strings like 'CAP-003 图像主体一致性保持')."""
    strat = body.get('strategy', {})
    phases = strat.get('phases', []) if isinstance(strat, dict) else []
    wo = []
    for ph in phases:
        if not isinstance(ph, dict): continue
        caps_used = ph.get('capabilities_used', [])
        resolved = []
        seen = set()
        for cu in caps_used:
            r = resolve_cap(cu, alias, m2c, db_caps, unresolved)
            if r and r not in seen:
                resolved.append({'id': r, 'name': db_caps.get(r, cu)})
                seen.add(r)
        wo.append({
            'phase': ph.get('phase', ''),
            'description': ph.get('description', ''),
            'capabilities': resolved,
        })
    return wo


def salvage_req_053(body, alias, m2c, db_caps, unresolved):
    """body.phases (top-level) with capabilities[*] dict."""
    phases = body.get('phases', [])
    wo = []
    for ph in phases:
        if not isinstance(ph, dict): continue
        caps_list = ph.get('capabilities', [])
        resolved = []
        seen = set()
        for c in caps_list:
            if not isinstance(c, dict): continue
            cid = c.get('id')
            name = c.get('name', '')
            # combined ref
            ref = cid if cid else name
            r = resolve_cap(ref, alias, m2c, db_caps, unresolved)
            if not r and name:
                r = resolve_cap(name, alias, m2c, db_caps, unresolved)
            if r and r not in seen:
                resolved.append({'id': r, 'name': db_caps.get(r, name)})
                seen.add(r)
        wo.append({
            'phase': ph.get('phase', ''),
            'description': ph.get('description', ''),
            'capabilities': resolved,
        })
    return wo


def salvage_req_066(body, alias, m2c, db_caps, unresolved):
    """body.execution_phases[*].capabilities_used (mixed id/name strings)."""
    phases = body.get('execution_phases', [])
    wo = []
    for ph in phases:
        if not isinstance(ph, dict): continue
        caps_used = ph.get('capabilities_used', [])
        resolved = []
        seen = set()
        for cu in caps_used:
            r = resolve_cap(cu, alias, m2c, db_caps, unresolved)
            if r and r not in seen:
                resolved.append({'id': r, 'name': db_caps.get(r, cu)})
                seen.add(r)
        wo.append({
            'phase': ph.get('phase', ''),
            'description': ph.get('description', ''),
            'capabilities': resolved,
        })
    return wo


def salvage_req_070(body, alias, m2c, db_caps, unresolved):
    """body.selected_blueprint.phases[*].capabilities_used."""
    sbp = body.get('selected_blueprint', {})
    if isinstance(sbp, str):
        try: sbp = json.loads(sbp)
        except: sbp = {}
    phases = sbp.get('phases', []) if isinstance(sbp, dict) else []
    wo = []
    for ph in phases:
        if not isinstance(ph, dict): continue
        caps_used = ph.get('capabilities_used', [])
        resolved = []
        seen = set()
        for cu in caps_used:
            r = resolve_cap(cu, alias, m2c, db_caps, unresolved)
            if r and r not in seen:
                resolved.append({'id': r, 'name': db_caps.get(r, cu)})
                seen.add(r)
        wo.append({
            'phase': ph.get('phase', ''),
            'description': ph.get('description', ''),
            'capabilities': resolved,
        })
    return wo


SALVAGERS = {
    'REQ_004': salvage_req_004,
    'REQ_031': salvage_req_031,
    'REQ_053': salvage_req_053,
    'REQ_066': salvage_req_066,
    'REQ_070': salvage_req_070,
}


# ═══════════════════════════════════════════════════════════
def main():
    s = PostgreSQLCapabilityStore()
    cur = s._get_cursor()
    try:
        alias, m2c, db_caps = build_alias_and_member(cur)
        print(f'alias entries: {len(alias)}, members: {len(m2c)}, db caps: {len(db_caps)}', flush=True)

        for req_id in TARGET_REQS:
            print(f'\n=== {req_id} ===', flush=True)
            cur.execute("""SELECT s.id, s.name, s.body FROM strategy s
                           JOIN requirement_strategy rs ON rs.strategy_id=s.id
                           WHERE rs.requirement_id=%s""", (req_id,))
            row = cur.fetchone()
            if not row:
                print(f'  ⚠️ no strategy found for {req_id}', flush=True)
                continue
            strat_id, strat_name = row['id'], row['name']
            body = row['body'] if isinstance(row['body'], dict) else json.loads(row['body'] or '{}')

            unresolved = []
            salvager = SALVAGERS[req_id]
            wo = salvager(body, alias, m2c, db_caps, unresolved)
            phase_count = len(wo)
            cap_total = sum(len(ph['capabilities']) for ph in wo)
            unique_caps = set()
            for ph in wo:
                for c in ph['capabilities']:
                    unique_caps.add(c['id'])

            print(f'  strategy: {strat_id} ({strat_name})', flush=True)
            print(f'  produced: {phase_count} phases, {cap_total} cap slots ({len(unique_caps)} unique)', flush=True)
            if unresolved:
                print(f'  unresolved refs: {len(unresolved)}', flush=True)
                for u in unresolved[:5]: print(f'    - {u!r}', flush=True)

            # Add workflow_outline to body (preserve all original fields)
            body['workflow_outline'] = wo
            body['_salvaged_at'] = '2026-04-22'
            body['_salvage_source'] = 'salvage_placeholder_strategies.py'

            # Update strategy.body
            cur.execute('UPDATE strategy SET body = %s WHERE id = %s',
                        (json.dumps(body, ensure_ascii=False), strat_id))

            # Write strategy_capability junction
            # First remove existing (should be 0 but be safe)
            cur.execute('DELETE FROM strategy_capability WHERE strategy_id = %s', (strat_id,))
            for cap_id in unique_caps:
                cur.execute("""INSERT INTO strategy_capability (strategy_id, capability_id, relation_type)
                               VALUES (%s, %s, 'compose') ON CONFLICT DO NOTHING""", (strat_id, cap_id))

            print(f'  wrote strategy_capability: {len(unique_caps)} rows', flush=True)

            # Verify: count strat_cap rows
            cur.execute('SELECT COUNT(*) c FROM strategy_capability WHERE strategy_id=%s', (strat_id,))
            print(f'  strategy_capability after: {cur.fetchone()["c"]}', flush=True)

        # Final verification
        print(f'\n{"="*60}', flush=True)
        print('All 5 placeholder strategies after salvage:', flush=True)
        for req_id in TARGET_REQS:
            cur.execute("""SELECT s.id, s.name,
                             (SELECT COUNT(*) FROM strategy_capability sc WHERE sc.strategy_id=s.id) cap_n
                           FROM strategy s
                           JOIN requirement_strategy rs ON rs.strategy_id=s.id
                           WHERE rs.requirement_id=%s""", (req_id,))
            r = cur.fetchone()
            if r:
                print(f'  [{req_id}] {r["id"]} ({r["name"]}): strat_cap={r["cap_n"]}', flush=True)
    finally:
        cur.close()
        s.close()


if __name__ == '__main__':
    main()